Initial commit

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,70 @@
+---
+library_name: stable-baselines3
+tags:
+- Swimmer-v3
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: TQC
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Swimmer-v3
+      type: Swimmer-v3
+    metrics:
+    - type: mean_reward
+      value: 319.81 +/- 2.40
+      name: mean_reward
+      verified: false
+---
+
+# **TQC** Agent playing **Swimmer-v3**
+This is a trained model of a **TQC** agent playing **Swimmer-v3**
+using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
+and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
+
+The RL Zoo is a training framework for Stable Baselines3
+reinforcement learning agents,
+with hyperparameter optimization and pre-trained agents included.
+
+## Usage (with SB3 RL Zoo)
+
+RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
+SB3: https://github.com/DLR-RM/stable-baselines3<br/>
+SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
+
+Install the RL Zoo (with SB3 and SB3-Contrib):
+```bash
+pip install rl_zoo3
+```
+
+```
+# Download model and save it into the logs/ folder
+python -m rl_zoo3.load_from_hub --algo tqc --env Swimmer-v3 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo tqc --env Swimmer-v3  -f logs/
+```
+
+If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
+```
+python -m rl_zoo3.load_from_hub --algo tqc --env Swimmer-v3 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo tqc --env Swimmer-v3  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo tqc --env Swimmer-v3 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo tqc --env Swimmer-v3 -f logs/ -orga qgallouedec
+```
+
+## Hyperparameters
+```python
+OrderedDict([('gamma', 0.9999),
+             ('learning_starts', 10000),
+             ('n_timesteps', 1000000.0),
+             ('policy', 'MlpPolicy'),
+             ('normalize', False)])
+```

args.yml

@@ -0,0 +1,83 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - tqc
+  - - conf_file
+    - null
+  - - device
+    - auto
+  - - env
+    - Swimmer-v3
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 20
+  - - eval_freq
+    - 25000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - logs
+  - - log_interval
+    - -1
+  - - max_total_trials
+    - null
+  - - n_eval_envs
+    - 5
+  - - n_evaluations
+    - null
+  - - n_jobs
+    - 1
+  - - n_startup_trials
+    - 10
+  - - n_timesteps
+    - -1
+  - - n_trials
+    - 500
+  - - no_optim_plots
+    - false
+  - - num_threads
+    - -1
+  - - optimization_log_path
+    - null
+  - - optimize_hyperparameters
+    - false
+  - - progress
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 3962785800
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - runs/Swimmer-v3__tqc__3962785800__1676710082
+  - - track
+    - true
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1
+  - - wandb_entity
+    - openrlbenchmark
+  - - wandb_project_name
+    - sb3
+  - - wandb_tags
+    - []
+  - - yaml_file
+    - null

config.yml

@@ -0,0 +1,9 @@
+!!python/object/apply:collections.OrderedDict
+- - - gamma
+    - 0.9999
+  - - learning_starts
+    - 10000
+  - - n_timesteps
+    - 1000000.0
+  - - policy
+    - MlpPolicy

env_kwargs.yml

@@ -0,0 +1 @@
+{}

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c6fa17e01f55d42809b52c258afce632f210844ac48e3901dc628473dbb6b23
+size 1303985

results.json

@@ -0,0 +1 @@
+{"mean_reward": 319.8090664, "std_reward": 2.40137736697631, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-28T18:04:32.355996"}

tqc-Swimmer-v3.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e3f499656a3b76dd94cd280760d7135f1f032b7b26c600a9adc9efdb3dd4dcb
+size 3279816

tqc-Swimmer-v3/_stable_baselines3_version

@@ -0,0 +1 @@
+1.8.0a6

tqc-Swimmer-v3/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc5810570cd1b81eb0928ae96623127dca59d44f3657b4b7922dcb6a3ccaa77
+size 559517

tqc-Swimmer-v3/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52bb4be65e79092e478c71f793f8bdd67b83a816c7c09342d304ca281e818020
+size 1210105

tqc-Swimmer-v3/data

@@ -0,0 +1,115 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVKgAAAAAAAACMGHNiM19jb250cmliLnRxYy5wb2xpY2llc5SMCVRRQ1BvbGljeZSTlC4=",
+        "__module__": "sb3_contrib.tqc.policies",
+        "__doc__": "\n    Policy class (with both actor and critic) for TQC.\n\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param lr_schedule: Learning rate schedule (could be constant)\n    :param net_arch: The specification of the policy and value networks.\n    :param activation_fn: Activation function\n    :param use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` when using gSDE to ensure\n        a positive standard deviation (cf paper). It allows to keep variance\n        above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n    :param clip_mean: Clip the mean output when using gSDE to avoid numerical instability.\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the feature extractor.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    :param n_quantiles: Number of quantiles for the critic.\n    :param n_critics: Number of critic networks to create.\n    :param share_features_extractor: Whether to share or not the features extractor\n        between the actor and the critic (this saves computation time)\n    ",
+        "__init__": "<function TQCPolicy.__init__ at 0x7ff9203a6670>",
+        "_build": "<function TQCPolicy._build at 0x7ff9203a6700>",
+        "_get_constructor_parameters": "<function TQCPolicy._get_constructor_parameters at 0x7ff9203a6790>",
+        "reset_noise": "<function TQCPolicy.reset_noise at 0x7ff9203a6820>",
+        "make_actor": "<function TQCPolicy.make_actor at 0x7ff9203a68b0>",
+        "make_critic": "<function TQCPolicy.make_critic at 0x7ff9203a6940>",
+        "forward": "<function TQCPolicy.forward at 0x7ff9203a69d0>",
+        "_predict": "<function TQCPolicy._predict at 0x7ff9203a6a60>",
+        "set_training_mode": "<function TQCPolicy.set_training_mode at 0x7ff9203a6af0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7ff9203a90c0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "use_sde": false
+    },
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float64",
+        "_shape": [
+            8
+        ],
+        "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
+        "high": "[inf inf inf inf inf inf inf inf]",
+        "bounded_below": "[False False False False False False False False]",
+        "bounded_above": "[False False False False False False False False]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            2
+        ],
+        "low": "[-1. -1.]",
+        "high": "[1. 1.]",
+        "bounded_below": "[ True  True]",
+        "bounded_above": "[ True  True]",
+        "_np_random": "RandomState(MT19937)"
+    },
+    "n_envs": 1,
+    "num_timesteps": 1000000,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1676710084880565805,
+    "learning_rate": 0.0003,
+    "tensorboard_log": "runs/Swimmer-v3__tqc__3962785800__1676710082/Swimmer-v3",
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVtQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZAAAAAAAAAAOx7Klbsp+m/LbYKYEck8T81IONgTRnfPzTlgaG78s0/EXRC9zek47+2YubEF0G0P3X/vTX2Pv+/bUJMzhraEUCUjAVudW1weZSMBWR0eXBllJOUjAJmOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLCIaUjAFDlHSUUpQu"
+    },
+    "_episode_num": 1000,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": 0.0,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 990000,
+    "buffer_size": 1,
+    "batch_size": 256,
+    "learning_starts": 10000,
+    "tau": 0.005,
+    "gamma": 0.9999,
+    "gradient_steps": 1,
+    "optimize_memory_usage": false,
+    "replay_buffer_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
+        "__module__": "stable_baselines3.common.buffers",
+        "__doc__": "\n    Replay buffer used in off-policy algorithms like SAC/TD3.\n\n    :param buffer_size: Max number of element in the buffer\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param device: PyTorch device\n    :param n_envs: Number of parallel environments\n    :param optimize_memory_usage: Enable a memory efficient variant\n        of the replay buffer which reduces by almost a factor two the memory used,\n        at a cost of more complexity.\n        See https://github.com/DLR-RM/stable-baselines3/issues/37#issuecomment-637501195\n        and https://github.com/DLR-RM/stable-baselines3/pull/28#issuecomment-637559274\n        Cannot be used in combination with handle_timeout_termination.\n    :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n        separately and treat the task as infinite horizon task.\n        https://github.com/DLR-RM/stable-baselines3/issues/284\n    ",
+        "__init__": "<function ReplayBuffer.__init__ at 0x7ff92082e5e0>",
+        "add": "<function ReplayBuffer.add at 0x7ff92082e670>",
+        "sample": "<function ReplayBuffer.sample at 0x7ff92082e700>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7ff92082e790>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7ff920829300>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "target_entropy": -2.0,
+    "ent_coef": "auto",
+    "target_update_interval": 1,
+    "top_quantiles_to_drop_per_net": 2,
+    "batch_norm_stats": [],
+    "batch_norm_stats_target": []
+}

tqc-Swimmer-v3/ent_coef_optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19fb25adf65b03f4f4453d38ee2238ee581ee231c207abcb8138099100e366fa
+size 1507

tqc-Swimmer-v3/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad851cb8d56da342861b5212e6c32089c065860668b67eaa6981e03d235ed08d
+size 1487877

tqc-Swimmer-v3/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6946c9971e5ef03732970f009c2a637273b3a04e1ff34b95ccd77ba9f1f8242f
+size 747

tqc-Swimmer-v3/system_info.txt

@@ -0,0 +1,7 @@
+- OS: Linux-5.19.0-32-generic-x86_64-with-glibc2.35 # 33~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Mon Jan 30 17:03:34 UTC 2
+- Python: 3.9.12
+- Stable-Baselines3: 1.8.0a6
+- PyTorch: 1.13.1+cu117
+- GPU Enabled: True
+- Numpy: 1.24.1
+- Gym: 0.21.0

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e08e945c961a394f5f2ca0dabbefdacce6171df5dfbc47dbfaab534f8ca16af
+size 42356